12,000 IRMA images from 116 categories for ImageCLEFmed 2007

<strong>Remark</strong><br>On this page, you can access data that has been used in several scientific studies. In order to make the results comparable, these datasets are available for other non-commercial evaluations. <strong>Description</strong><br>This collection compiles anonymous radiographs, which have been arbitrarly selected from routine at the Department of Diagnostic Radiology, Aachen University of Technology (RWTH), Aachen, Germany. The imagery represents different ages, genders, view positions and pathologies. Therefore, image quality varies significantly. All images were downscaled to fit into a 512 x 512 bounding box maintaining the original aspect ratio. All images were classified according to the IRMA code. Based on this code, 116 categories were defined. For 11,000 images, these categories are provided. The remaining 1,000 images without code are used as test data for the ImageCLEFmed 2007 competition.Training data: 10,000 radiographs in 116 categoriesExtended training data: further 1,000 radiographs for extended trainingClass distribution: Distritbution of classes in the training data.Test data: 1,000 radiographs without classification.